Model card for centerpoint-voxel0075.nuscenes.mmdet3d

A CenterPoint 3D object detection model (center-based detector over a BEV heatmap). Trained on nuScenes.

Model Details

Model Type: 3D object detection
Model Stats:
- Params (M): 8.9
- Input channels: 5
- Classes: 10
- Features: 512
Dataset: nuScenes
Metrics: mAP 57.06, NDS 65.04
Paper: Center-based 3D Object Detection and Tracking
Converted from: open-mmlab/mmdetection3d (Apache-2.0)
Library: torch-pointcloud

Install

pip install torch-pointcloud

This checkpoint also needs spconv, which needs a build matching your torch and CUDA: see the installation guide.

Usage

import torch
import torch_pointcloud as tp
from torch_pointcloud.utils.data import collate

model, info = tp.create_model(
    "centerpoint-voxel0075.nuscenes.mmdet3d",
    pretrained=True,
    return_info=True,
)
model = model.cuda().eval()  # GPU-only kernels

# synthetic sample with the keys a dataset provides
num_points = 8192
sample = {
    "pos": torch.randn(num_points, 3),
    "intensity": torch.rand(num_points, 1),
    "timestamp": torch.zeros(num_points, 1),
}
data = info["transform"](sample)
data = collate([data], batch_from="pos_voxel")
data = {key: value.cuda() for key, value in data.items()}

with torch.no_grad():
    out = model(data["voxel"], data["pos_voxel"], data["voxel_num_points"], data["batch"])

Feature extraction

with torch.no_grad():
    features = model.forward_features(
        data["voxel"],
        data["pos_voxel"],
        data["voxel_num_points"],
        data["batch"],
    )  # 512 channels

Citation